Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by bradleygolden • Documentation & Docs
An MCP server that provides semantic search over Hex package documentation for AI clients.
Semantically search Hex package documentation to answer questions about library APIs and usage examples.
Automatically fetch and index specific package versions (or project-linked versions) and keep local embeddings for fast retrieval.
An MCP-compatible server to integrate package docs search into MCP clients like Cursor, Claude Desktop, or other tooling.
HexDocs MCP is a two-part tool: an Elixir binary that downloads, processes, and generates embeddings from Hex package documentation, and a TypeScript MCP server that exposes search and fetch capabilities via the Model Context Protocol. It enables AI agents and MCP-compatible clients to automatically fetch, index, and semantically search Hex docs, with embeddings generated via Ollama. The project simplifies integrating package documentation into agent workflows and automates storage and retrieval of vector embeddings for fast, context-aware responses.
Searches the documentation of one or more Elixir Hex packages using semantic vector embeddings. Given a natural language query, returns the most relevant documentation snippets. Requires that embeddings have been generated for the target package(s) using the fetch tool.
Downloads and processes the documentation for a specified Elixir Hex package and version, converting it to markdown, splitting it into semantic chunks, and generating vector embeddings. This enables fast and accurate semantic search with the search tool. Must be run before searching a package for the first time or to update embeddings.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.